A Probabilistic Answer Type Model

A Probabilistic Answer Type Model Christopher Pinchak Department of Computing Science University of Alberta Edmonton, Alberta, Canada pinchak@cs.ualberta.ca Dekang Lin Google, Inc. 1600 Amphitheatre Parkway Mountain View, CA lindek@google.com Abstract All questions are implicitly associated with an expected answer type. Unlike previous approaches that require a prede- fined set of question types, we present a method for dynamically constructing a probability-based answer type model for each different question. Our model evaluates the appropriateness of a poten- tial answer by the probability that it fits into the question contexts. Evaluation is performed against manual and semi- automatic methods using a fixed set of an- swer labels. Results show our approach to be superior for those questions classified as having a miscellaneous answer type. 1 Introduction Given a question, people are usually able to form an expectation about the type of the answer, even if they do not know the actual answer. An accu- rate expectation of the answer type makes it much easier to select the answer from a sentence that contains the query words. Consider the question “What is the capital of Norway?” We would ex- pect the answer to be a city and could filter out most of the words in the following sentence: The landed aristocracy was virtually crushed by Hakon V, who reigned from 1299 to 1319, and Oslo became the capital of Norway, re- placing Bergen as the principal city of the kingdom. The goal of answer typing is to determine whether a word’s semantic type is appropriate as an answer for a question. Many previous ap- proaches to answer typing, e.g., (Ittycheriah et al., 2001; Li and Roth, 2002; Krishnan et al., 2005), employ a predefined set of answer types and use supervised learning or manually constructed rules to classify a question according to expected an- swer type. A disadvantage of this approach is that there will always be questions whose answers do not belong to any of the predefined types. Consider the question: “What are tourist attrac- tions in Reims?” The answer may be many things: a church, a historic residence, a park, a famous intersection, a statue, etc. A common method to deal with this problem is to define a catch-all class. This class, however, tends not to be as effective as other answer types. Another disadvantage of predefined answer types is with regard to granularity. If the types are too specific, they are more difficult to tag. If they are too general, too many candidates may be identified as having the appropriate type. In contrast to previous approaches that use a su- pervised classifier to categorize questions into a predefined set of types, we propose an unsuper- vised method to dynamically construct a proba- bilistic answer type model for each question. Such a model can be used to evaluate whether or not a word fits into the question context. For exam- ple, given the question “What are tourist attrac- tions in Reims?”, we would expect the appropriate answers to fit into the …

Content truncated to 500 words